Search Results (87)

Background/Objectives: Radiomics-based machine learning models have demonstrated high accuracy in differentiating benign from malignant orbital masses, with early studies suggesting performance comparable to expert radiologists. However, translation into clinical practice remains limited due to dataset constraints, including retrospective study designs, single-center cohorts, and underrepresentation of diverse patient populations. This review aims to evaluate the current evidence supporting radiomics in orbital disease while critically examining barriers to generalizability and equity across ophthalmology, otolaryngology, and plastic surgery. Methods: A narrative literature review was conducted to assess radiomics applications in orbital oncology and reconstruction. Studies evaluating diagnostic accuracy, margin assessment, postoperative surveillance, and surgical planning across ophthalmology, head and neck surgery, and reconstructive surgery were analyzed, with particular attention paid to dataset composition, validation strategies, and imaging standardization. Results: Radiomics models demonstrated high diagnostic performance in differentiating orbital tumors, optimizing surgical planning, and aiding postoperative monitoring. However, most studies relied on small, homogeneous datasets lacking racial, ethnic, and pediatric representation. External validation was uncommon, and imaging heterogeneity limited reproducibility. These deficiencies restrict the clinical translation of radiomics and risk exacerbating healthcare disparities, particularly among underrepresented populations. Conclusions: Radiomics holds promise as a precision medicine tool for orbital diagnosis, surgical navigation, and postoperative care. Nevertheless, its clinical adoption is constrained by dataset bias, lack of standardization, and limited prospective validation. Future progress requires multi-institutional, demographically diverse datasets and standardized imaging protocols to ensure equitable and generalizable implementation across specialties. Full article

Incomplete or faulty MRI sequences are common in clinical practice and can impair AI-based analyses that rely on complete multi-contrast data. The relative effectiveness of classical generative adversarial networks (GANs) versus modern diffusion and transformer-based models for clinically usable MRI synthesis remains unclear. This study evaluates cross-modality MRI synthesis using the BraTS 2019 brain tumour dataset, focusing on T1-to-T2 translation. We assess paired and unpaired CycleGAN models and compare them with two stronger but computationally intensive baselines, a conditional denoising diffusion probabilistic model (DDPM) and a transformer-enhanced GAN, using identical data splits and preprocessing pipelines. Inter-modality correlation was evaluated to estimate the achievable similarity between modalities. Conceptually, modality synthesis may be viewed as a representation-learning approach that compensates for missing imaging information by reconstructing clinically relevant features from available contrasts. Paired CycleGAN achieved correlations of $r\approx 0.92–0.93$ and SSIM $\approx 0.90–0.92$, approaching natural T1–T2 correlation ($r\approx 0.95$) while maintaining very fast inference (<50 ms/slice). Unpaired CycleGAN achieved $r\approx 0.74–0.78$ and SSIM $\approx 0.82–0.85$, producing clinically interpretable reconstructions without voxel-level supervision. DDPM achieved the highest fidelity (SSIM $\approx 0.93–0.95$, $r\approx 0.94$) but required substantially greater computational resources, while transformer-enhanced GAN performance was intermediate. Qualitative analysis showed that CycleGAN and DDPM best preserved tumour and tissue boundaries, whereas unpaired CycleGAN occasionally over-smoothed subtle lesions. These findings highlight the trade-off between fidelity and efficiency in cross-modality MRI synthesis, suggesting paired CycleGAN for time-sensitive clinical workflows and diffusion models as a computationally expensive accuracy upper bound. Full article

Background: The use of augmented reality (AR) in orthopaedics is growing rapidly but is mainly limited to pre-operative planning and teaching. This study is one of the first to describe the intraoperative application within revision arthroplasty for the positioning of customised partial pelvic replacements. Methods: In a proof-of-concept study an AR environment was used during surgery in 11 cases to enhance implant positioning. Postoperatively, a voxel-based CT deviation analysis was carried out to determine the COR deviation and the cup plane deviation angle. Additionally, digital implant superimposition was conducted. Results: Implantation was possible in all cases with a mean COR deviation vector of 4.2 (SD 2.5; 1.2–9.3) mm and a cup plane deviation angle of 4.4 (SD 2.5; 0.7–8.1)°. The implant analysis showed a superimposition of 0.69 (SD 0.15; 0.38–0.88) (Dice-Score calculation). Conclusions: This study is able to report promising results for AR in orthopaedic surgery, showing improved intraoperative feedback in complex operations, resulting in increased accuracy. However, the integration of AR poses a new challenge to the surgical team, especially because the AR users are facing a significantly increased level of intraoperative stress. Further development of this auspicious tool, as well as a conceivable combination with navigation, is necessary to facilitate broader usage. Full article

Dynamic contrast-enhancement (DCE) modality of MRI is typically considered secondary in prostate cancer (PCa) diagnostics, due to the common interpretation that its diagnostic power is lower than that of other modalities like T2-weighted (T2W) or diffusion-weighted imaging (DWI). To challenge this paradigm, this study introduces a novel concept of a difference map, which relies exclusively on DCE-MRI for the localization of peripheral zone prostate cancer using functional data analysis-based (FDA) signal processing. The proposed workflow uses discrete voxel-level DCE time–signal curves that are transformed into a continuous functional form. First-order derivatives are then used to determine patient-specific time points of greatest enhancement change that adapt to the intrinsic characteristics of each patient, producing diffmaps that highlight regions with pronounced enhancement dynamics, indicative of malignancy. A subsequent normalization step accounts for inter-patient variability, enabling consistent interpretation across subjects and probabilistic PCa localization. The approach is validated on a curated dataset of 20 patients. Evaluation of eight workflow variants is performed using weighted log loss, the best variant achieving a mean log loss of 0.578. This study demonstrates the feasibility and effectiveness of a single-modality, automated, and interpretable approach for peripheral prostate cancer localization based solely on DCE-MRI. Full article

Actinium-225 (²²⁵Ac) has emerged as a pivotal alpha-emitter in modern radiopharmaceutical therapy, offering potent cytotoxicity with the potential for precise tumour targeting. Accurate, patient-specific image-based dosimetry for ²²⁵Ac is essential to optimize therapeutic efficacy while minimizing radiation-induced toxicity. Establishing a robust dosimetry workflow is particularly challenging due to the complex decay chain, low administered activity, limited count statistics, and the indirect measurement of daughter gamma emissions. Clinical single-photon emission computed tomography/computed tomography protocols with harmonized acquisition parameters, combined with robust volume-of-interest segmentation, artificial intelligence (AI)-driven image processing, and voxel-level analysis, enable reliable time-activity curve generation and absorbed-dose calculation, while reduced mixed-model approaches improve workflow efficiency, reproducibility, and patient-centred implementation. Cadmium zinc telluride-based gamma cameras further enhance quantitative accuracy, enabling rapid whole-body imaging and precise activity measurement, supporting patient-friendly dosimetry. Complementing these advances, the cerium-134/lanthanum-134 positron emission tomography in vivo generator provides a unique theranostic platform to noninvasively monitor ²²⁵Ac progeny redistribution, evaluate alpha-decay recoil, and study tracer internalization, particularly for internalizing vectors. Together, these technological and methodological innovations establish a mechanistically informed framework for individualized ²²⁵Ac dosimetry in targeted alpha therapy, supporting optimized treatment planning and precise response assessment. Continued standardization and validation of imaging, reconstruction, and dosimetry workflows will be critical to translate these approaches into reproducible, patient-specific clinical care. Full article

Urban mobility systems increasingly depend on remote sensing and artificial intelligence to enhance traffic monitoring and safety management. This study presents a LiDAR-based framework for urban road condition analysis and risk evaluation using vehicle-mounted sensors as dynamic remote sensing platforms. The framework integrates deep learning based object detection with mathematically defined surrogate safety indicators to quantify collision risk and evaluate evasive maneuverability in real traffic environments. Two indicators, Hazardous Modified Time to Collision (HMTTC) and Searching for Safety Space (SSS), are introduced to assess lane-level safety and spatial availability of avoidance zones. LiDAR point cloud data are processed using a Voxel RCNN architecture and converted into parameters such as density, speed, and spacing. Field experiments conducted on highways and urban corridors in South Korea reveal strong correlations between HMTTC occurrences, congestion, and geometric road features. The results demonstrate that AI-driven analysis of LiDAR data enables continuous, infrastructure-independent urban traffic safety monitoring, thereby supporting data-driven, resilient transportation systems. Full article

Background/Objectives: Radiotherapy, radiobiology, and oncology have evolved rapidly over the past six decades. This progress has generated vast but fragmented bodies of scientific evidence. The present study aimed to systematically map and interpret their conceptual and temporal development using artificial intelligence (AI)-based methods. It highlights the integration between molecular mechanisms, clinical applications, and technological innovation within a precision radiotherapy framework. Methods: A corpus of 3343 unique articles (1964–2025) was retrieved from Scopus, PubMed, and Web of Science. Records were harmonized through deduplication, lemmatization, and metadata normalization. Topic modeling using Latent Dirichlet Allocation (LDA) and co-occurrence network analysis were applied to identify dominant research axes. Semantic and temporal analyses were conducted to reveal patterns, emerging trends, and translational connections across decades. Results: Three historical phases were identified. The first was a period of limited production (1964–1990). The second showed moderate growth (1991–2010). The third, from 2011 to 2024, represented exponential expansion, with publication peaks in 2020 and 2023. LDA revealed two principal axes. The first, a clinical–anatomical axis, focused on cancer sites, treatment modalities, and prognosis. The second, a mechanistic–molecular axis, centered on DNA repair, radiosensitivity, and biomarkers. Case synthesis from 2014–2025 defined five operational classes: DNA repair and molecular response; precision oncology and genomic modeling; individual radiosensitivity; mechanisms of radioresistance; and advanced technologies such as FLASH radiotherapy and optimized brachytherapy. Conclusions: AI-driven semantic and temporal analyses showed that radiotherapy has matured into an interconnected and interdisciplinary domain. The derived Precision Radiotherapy Implementation Plan translates molecular and computational insights into clinically actionable strategies. These approaches can enhance survival, reduce toxicity, and inform equitable health policies for advanced cancer care. Full article

Background: Hepatocellular carcinoma (HCC), the most prevalent primary malignancy of the liver, is commonly treated with transarterial chemoembolization (TACE), a locoregional therapy that combines targeted intra-arterial chemotherapy with selective embolization to induce tumor ischemia and necrosis. However, current methods for monitoring the treatment response—such as the RECIST and mRECIST—often fail to detect early or subtle biological changes, such as tumor necrosis or microstructural remodeling, and therefore may underestimate the therapeutic effects, especially in cases with minimal or delayed tumor shrinkage. Thus, there is a critical need for quantitative imaging strategies that can improve early response assessment and guide more personalized treatment decision-making. The goal of this study was to assess the changes in computed tomography (CT) perfusion parameters and radiomic features in HCC before and after TACE and to evaluate the associations of these parameters/features with the tumor burden. Methods: In this retrospective, single-center study, 32 patients with histologically confirmed HCC underwent CT perfusion and radiomic analysis prior to and following TACE. Multiple quantitative perfusion parameters (arterial flow, perfusion flow, perfusion index) and radiomic features were extracted. Statistical comparisons were performed using the Wilcoxon signed-rank test and Spearman’s correlation. Radiomic feature extraction was performed in strict adherence to the Image Biomarker Standardization Initiative (IBSI) guidelines. Preprocessing steps included voxel resampling (1 × 1 × 1 mm), z-score normalization, and fixed bin-width discretization (bin width = 25). All tumor ROIs were manually segmented in consensus by two experienced radiologists to minimize inter-observer variability. Results: Arterial flow significantly decreased from a median of 56.5 to 47.7 mL/100 mL/min after TACE (p = 0.009), while nonsignificant increases in the perfusion flow (from 101.3 to 107.8 mL/100 mL/min, p = 0.44) and decreases in the perfusion index (from 38.6% to 35.7%, p = 0.25) were also observed. Perfusion flow was strongly and positively correlated with tumor size (ρ = 0.94, p < 0.001). Five radiomic texture feature values—especially those of ShortRunHighGrayLevelEmphasis (Δ = +2.11, p = 0.0001) and LargeAreaHighGrayLevelEmphasis (Δ = +75,706, p = 0.0006)—changed significantly after treatment. These radiomic feature value changes were more pronounced in tumors ≥50 mm in diameter. In addition, we performed a receiver operating characteristic (ROC) analysis of the two most discriminative radiomic features (SRHGLE and LAHGLE). We further developed a multivariable logistic regression model that achieved an AUC of 0.87, supporting the potential of these features as predictive biomarkers. Conclusions: CT perfusion and radiomics offer complementary insights into the treatment response of patients with HCC. While perfusion parameters reflect macroscopic vascular changes and are correlated with tumor burden, radiomic features can indicate microstructural changes after TACE. This combined imaging approach may improve early therapeutic assessment and support precision oncology strategies. Full article

Localized ¹H magnetic resonance spectroscopy (MRS) is a powerful tool in pre-clinical and clinical neurological research, offering non-invasive insight into neurochemical composition in localized brain regions. Zebrafish (Danio rerio) are increasingly being utilized as models in neurological disorder research, providing valuable insights into disease mechanisms. However, the small size of the zebrafish brain and limited MRS sensitivity at low magnetic fields hinder comprehensive neurochemical analysis of localized brain regions. Here, we investigate the potential of ultra-high-field (UHF) MR systems, particularly 28.2 T, for this purpose. This present study pioneers the application of localized ¹H spectroscopy in zebrafish brain at 28.2 T. Point resolved spectroscopy (PRESS) sequence parameters were optimized to reduce the impact of chemical shift displacement error and to enable molecular level information from distinct brain regions. Optimized parameters included gradient strength, excitation frequency, echo time, and voxel volume specifically targeting the 0–4.5 ppm chemical shift regions. Exceptionally high-resolution cerebral metabolite spectra were successfully acquired from localized regions of the zebrafish brain in voxels as small as 125 nL, allowing for the identification and quantification of major brain metabolites with remarkable spectral clarity, including lactate, myo-inositol, creatine, alanine, glutamate, glutamine, choline (phosphocholine + glycerol-phospho-choline), taurine, aspartate, N-acetylaspartyl-glutamate (NAAG), N-acetylaspartate (NAA), and γ-aminobutyric acid (GABA). The unprecedented spatial resolution achieved in a small model organism enabled detailed comparisons of the neurochemical composition across distinct zebrafish brain regions, including the forebrain, midbrain, and hindbrain. This level of precision opens exciting new opportunities to investigate how specific diseases in zebrafish models influence the neurochemical composition of specific brain areas. Full article

Natural elements such as vegetation, water bodies, and sky, together with artificial elements including buildings and paved surfaces, constitute the core of urban visual environments. Their perception at the pedestrian level not only influences city image but also contributes to residents’ well-being and spatial experience. This study develops a hybrid 3D visibility assessment framework that integrates a city-scale LOD1 solid model with high-resolution mobile LiDAR point clouds to quantify five visual exposure indicators. The case study area is Yueya Lake Park in Nanjing, where a voxel-based line-of-sight sampling approach simulated eye-level visibility at 1.6 m along the southern lakeside promenade. Sixteen viewpoints were selected at 50 m intervals to capture spatial variations in visual exposure. Comparative analysis between the solid model (excluding vegetation) and the hybrid model (including vegetation) revealed that vegetation significantly reshaped the pedestrian visual field by reducing the dominance of sky and buildings, enhancing near-field greenery, and reframing water views. Artificial elements such as buildings and ground showed decreased exposure in the hybrid model, reflecting vegetation’s masking effect. The calculation efficiency remains a limitation in this study. Overall, the study demonstrates that integrating natural and artificial elements provides a more realistic and nuanced assessment of pedestrian visual perception, offering valuable support for sustainable landscape planning, canopy management, and the equitable design of urban public spaces. Full article

This perspective paper critically examines the emerging role of voxel-based analysis (VBA), also referred to as image-based data mining (IBDM), in dose–toxicity modeling for post-radiotherapy toxicity assessment. These techniques offer promising insights into localized organ subregions associated with toxicity, yet their current application faces substantial methodological and validation challenges. Based on prior studies and practical experience, we highlight seven key limitations: (i) lack of clinical validation for dose–toxicity models, (ii) strong dependence of results on statistical method selection (parametric vs. nonparametric), (iii) insensitivity of commonly used tests to uniform dose scaling, (iv) influence of tail selection (one- vs. two-tailed tests) on statistical power, (v) frequent misapplication of permutation testing, (vi) reliance on dose as the sole predictor while neglecting patient-, treatment-, and genomic-level covariates, and (vii) misinterpretation of voxel-wise associations as causal in the absence of appropriate causal inference frameworks. Collectively, these limitations can obscure clinically relevant dose differences, inflate false-positive or false-negative findings, obscure effect direction, introduce confounded associations, and ultimately yield inconsistent identification of high-risk subregions in organs at risk and poor reproducibility across studies. Notably, current univariable VBA/IBDM approaches should be regarded as hypothesis-generating rather than clinical decision-making tools, as unvalidated findings risk premature translation into clinical practice. Advancing personalized radiotherapy requires rigorous outcome validation, integration of multivariable and causal modeling strategies, and incorporation of clinical and genomic data. By moving beyond dose-only predictor models, VBA/IBDM can achieve greater biological relevance, reliability, and clinical utility, supporting more precise and individualized radiotherapy strategies. Full article

This paper presents a novel adversarial Convolutional Neural Network (ConvNet) method for generating adversarial perturbations in 3D point clouds, enabling gradient-free robustness evaluation of object detection systems at inference time. Unlike existing iterative gradient methods, our approach embeds the ConvNet directly into the detection pipeline at the voxel feature level. The ConvNet is trained to maximize detection loss while maintaining perturbations within sensor error bounds through multi-component loss constraints (intensity, bias, and imbalance terms). Evaluation on a Sparsely Embedded Convolutional Detection (SECOND) detector with the KITTI dataset shows 8% overall mean Average Precision (mAP) degradation, while CenterPoint on NuScenes exhibits 24% weighted mAP reduction across 10 object classes. Analysis reveals an inverse relationship between object size and adversarial vulnerability: smaller objects (pedestrians: 13%, cyclists: 14%) show higher vulnerability compared to larger vehicles (cars: 0.2%) on KITTI, with similar patterns on NuScenes, where barriers (68%) and pedestrians (32%) are most affected. Despite perturbations remaining within typical sensor error margins (mean L2 norm of 0.09% for KITTI, 0.05% for NuScenes, corresponding to 0.9–2.6 cm at typical urban distances), substantial detection failures occur. The key novelty is training a ConvNet to learn effective adversarial perturbations during a one-time training phase and then using the trained network for gradient-free robustness evaluation during inference, requiring only a forward pass through the ConvNet (1.2–2.0 ms overhead) instead of iterative gradient computation, making continuous vulnerability monitoring practical for autonomous driving safety assessment. Full article

Background/Objectives: Auditory sentence comprehension often remains impaired in individuals with post-stroke aphasia despite recovery in word-level comprehension. Neuroimaging studies have identified a left perisylvian network, especially temporal regions, as central to sentence comprehension, while the role of left frontal areas and specific white matter tracts remains debated. This study uses advanced fixel-based analysis (FBA) of diffusion MRI to precisely map white matter alterations related to complex sentence comprehension deficits in subacute Mandarin-speaking aphasic patients, addressing gaps from prior voxel-based and English-specific research. Methods: Twenty-three right-handed native Mandarin speakers with subacute (1–6 months post-onset) single left-hemisphere strokes underwent diffusion MRI. Standard preprocessing and FBA were conducted. Whole-brain linear regression assessed associations between fiber density and cross-section (FDC) and non-canonical sentence comprehension, controlling for age, education, time post-stroke, and verb comprehension. Mean FDC was calculated for each tract containing at least one significant fixel identified by FBA. Partial Spearman’s correlations examined relationships between mean FDC values within these tracts and comprehension accuracy for each sentence type, controlling for the same covariates. Results: Canonical sentences were comprehended significantly better than non-canonical sentences. FBA identified significant positive correlations between FDC and non-canonical sentence comprehension in the left superior longitudinal fasciculus (SLF II and SLF III), arcuate fasciculus (AF), middle longitudinal fasciculus, inferior fronto-occipital fasciculus, and the isthmus and splenium of the corpus callosum. Fiber density reduction primarily drove reductions in FDC, whereas reductions in fiber cross-section were limited to dorsal tracts (SLF III and AF). Conclusions: This study highlights a distributed left perisylvian white matter network critical for complex sentence comprehension in Mandarin speakers, refining neurocognitive models by identifying specific white matter substrates and demonstrating FBA’s utility in aphasia research. Full article

Background: Gliomas are among the most complex and lethal primary brain tumors, necessitating precise evaluation of both anatomical subregions and molecular alterations for effective clinical management. Methods: To find a solution to the disconnected nature of current bioimage analysis pipelines, where anatomical segmentation based on MRI and molecular biomarker prediction are done as separate tasks, we use here Molecular-Genomic and Multi-Task (MGMT-Net), a one deep learning scheme that carries out the task of the multi-modal MRI data without any conversion. MGMT-Net incorporates a novel Cross-Modality Attention Fusion (CMAF) module that dynamically integrates diverse imaging sequences and pairs them with a hybrid Transformer–Convolutional Neural Network (CNN) encoder to capture both global context and local anatomical detail. This architecture supports dual-task decoders, enabling concurrent voxel-wise tumor delineation and subject-level classification of key genomic markers, including the IDH gene mutation, the 1p/19q co-deletion, and the TERT gene promoter mutation. Results: Extensive validation on the Brain Tumor Segmentation (BraTS 2024) dataset and the combined Cancer Genome Atlas/Erasmus Glioma Database (TCGA/EGD) datasets demonstrated high segmentation accuracy and robust biomarker classification performance, with strong generalizability across external institutional cohorts. Ablation studies further confirmed the importance of each architectural component in achieving overall robustness. Conclusions: MGMT-Net presents a scalable and clinically relevant solution that bridges radiological imaging and genomic insights, potentially reducing diagnostic latency and enhancing precision in neuro-oncology decision-making. By integrating spatial and genetic analysis within a single model, this work represents a significant step toward comprehensive, AI-driven glioma assessment. Full article

In flank milling of thin-walled workpieces, machining deformation is a key issue affecting workpiece accuracy and process stability. Although the traditional finite element method (FEM) offers high accuracy, its low computational efficiency makes it difficult to meet the requirements for rapid prediction in engineering practice. For this purpose, this paper proposes an efficient method for predicting workpiece deformation based on the voxel octree model. First, based on the analysis of the contact position between the cutting tool and the workpiece, the thin-walled workpiece is divided into six levels of voxel units, using a voxel octree model. Then, the stiffness matrix and update model of the voxel units are established. Finally, the deformation prediction is completed by calculating the micro-milling force and the voxel stiffness matrix. The experimental results show that the workpiece deformation predicted by the proposed method is highly consistent with the actual machining measurement. At the same time, compared with traditional FEM and voxel model methods, the calculation time is reduced by 90% and 13.2%, respectively. This method can provide rapid decision support for the optimization of thin-walled workpiece machining processes and effectively improve the efficiency of preliminary research in actual machining. Full article